​ ​ ​ ​ Yixin Wang's Homepage ​ ​ ​ ​ ​ ​ ​ ​


Yixin Wang

I am a 2nd year Ph.D. student at Stanford University, working on AI + Healthcare.
I am fortunate to be co-advised by Dr. Kilian M. Pohl and Dr. Michael Zeineh.

Before starting my Ph.D., I got my master degree from Institute of Computing Technology, Chinese Academy of Sciences, majoring in Computer Science, supervised by Prof. Zhiqiang George He (Senior Vice President, Lenovo). Since Sept.2019, I have been an intern in AI Lab, Lenovo research, advised by Dr. Jianping Fan (Lenovo VP, Head of AI Lab) and Dr. Yong Rui (Fellow of ACM, IEEE, AAAS, IAPR, SPIE). Before that, I received B.Eng in Computer Science and Technology from Shandong University in 2019.

Contact: yxinwang -at- stanford dot edu
[Google Scholar] [Github] [Linkedin] [CV]

News

  • [02/2024] We have One Abstract on Correlative MR-Histology accepted at ISMRM 2024 (Oral)! I am awarded Student Travel Stipend!
  • [01/2024] We have One paper on Radiology Report Generation accepted at Neurocomputing!
  • [07/2023] We have One paper on Brain Measurement Imputation accepted at PRIME 2023!
  • [07/2023] We have One paper on Medical Knowledge Graph accepted at ICML IMLH 2023!
  • [06/2023] We have One paper accepted at MICCAI 2023! Congrats to Zhe!
  • [01/2023] We have one paper on Vision Transformer accepted at CVPR 2023! Congrats to Yang!
  • [11/2022] Our great survey on Deep learning in Single-Cell Analysis is online now!
  • [09/2022-12/2022] I was very fortunate to work with Prof. Bo Wang to integrate transformer language models into cross-species cell type mapping!
  • [09/2022] Start my PhD journal at Stanford! Moving to California! !
  • [06/20/2022] I am honored CAS Presidential Scholarship (Highest personal honor of Chinese Academy of Sciences)!
  • [10/26/2022] We have Two paper accepted at MICCAI 2022!
  • [05/23/2022] We have One paper accepted at ICASSP 2022!
  • [03/24/2022] We have One paper accepted at IEEE JBHI!
  • [11/17/2021] I am honored National Scholarship (Top 1%)!
  • [11/11/2021] Our survey on Visual Transformers is online now!
  • [10/26/2021] We have One paper accepted at IEEE TMRB!
  • [06/15/2021] We have Two papers accepted at MICCAI 2021!
  • [02/12/2021] Our paper is accepted at Computer Methods and Programs in Biomedicine!
  • [01/13/2021] I am honored Dean's Award!
  • [12/23/2020] Our paper on COVID-19 is accepted at Medical Physics!
  • [09/22/2020] We win the 2nd place in MICCAI M&Ms Challenge 2020!
  • [09/18/2020] We win the 2nd place in MICCAI BraTS Challenge 2020!
  • [04/23/2020] Our paper on Uncertainty & Semi-supervised is accepted at MICCAI 2020!
  • [01/04/2020] Our paper on Organ detection is accepted at ISBI 2020!

Research

Multi-Modal Analysis

    Medical databases include abundant information formats, such as imaging, texts, tabular data, and signals. Specifically, in medical imaging, there are different modalities such as MRI, CT, X-ray, PET, and so on. Different modalities are chosen to provide anatomical and functional information about organ and tissue structure. We design a Modality-Pairing Network to effectively capture the complementary information from multiple MRI modalities for brain tumor segmentation (MICCAI BraTS challenge 3rd prize)[PDF][Code]. We further focus on the challenging issue of missing modalities and propose an ACN network to enable a coupled learning process to enhance the learning ability of both full modalities and unimodal training [PDF][Code]. Besides, we explore the power of text & image in medical diagnosis. We explicitly quantify both the visual uncertainty and the textual uncertainty for DL-based medical report generation (MRG)[PDF]. We also establish a complete knowledge graph (KG) on chest X-ray imaging to address the long-tailed problem of disease distribution in current MRG datasets [PDF][Code].

Data-efficient Learning

    DL methods in medical imaging require high-quality annotated data for training and validation. However, obtaining perfectly labeled datasets in the medical domain is challenging. These problems can be addressed by 1) maximizing the benefit of existed labeled data or 2) leveraging the unlabeled data. To better utilize the unlabeled data, we developed a semi-supervised learning method which utilizes a teacher-student model to take advantage of unlabeled data [PDF]. While training a deep learning models with extremely limited labeled dataset, the model is easily running into over-parameterization. To tackle this issue, we further propose a Transfer learning (TL) framework where a Hybrid-encoder strategy based on multi-lesion pre-trained model to enhance model’s generalization for segmenting COVID-19 infection [PDF]. Due to the limited data sets, our knowledge about data (environment) & learning tasks could be incomplete at the training time. We do expect our AI system can learn to know unknowns (e.g., new disease) adaptively. Therefore, we design a novel cross-domain few-shot learning techniques, leveraging the power of natural data sets for rare skin disease segmentation [PDF].

Publications

​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​

Please check [ full list ] if you want :)

2023
Imputing Brain Measurements Across Data Sets via Graph Neural Networks,
Yixin Wang, Wei Peng, Susan F. Tapert, Qingyu Zhao, Kilian M. Pohl,
PRedictive Intelligence in Medicine (PRIME 2023) - MICCAI 2023 [PDF][Code]
Rethinking Medical Report Generation: Disease Revealing Enhancement with Knowledge Graph,
Yixin Wang, Zihao Lin, Haoyu Dong,
Workshop on Interpretable ML in Healthcare at International Conference on Machine Learning (ICML 2023) [PDF][Code]
Ambiguity-selective consistency regularization for mean-teacher semi-supervised medical image segmentation,
Zhe Xu, Yixin Wang, Donghuan Lu, Xiangde Luo, Jiangpeng Yan, Yefeng Zheng, Raymond Kai-yu Tong,
Medical Image Analysis [PDF][Code]
A survey of visual transformers,
Yang Liu, Yao Zhang, Yixin Wang, Feng Hou, Jin Yuan, Jiang Tian, Yang Zhang, Zhongchao Shi, Jianping Fan, Zhiqiang He,
IEEE Transactions on Neural Networks and Learning Systems (TNNLS) [PDF][Code]
Sap-detr: Bridging the gap between salient points and queries-based transformer detector for fast model convergency,
Yang Liu, Yao Zhang, Yixin Wang, Yang Zhang, Jiang Tian, Zhongchao Shi, Jianping Fan, Zhiqiang He,
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023) [PDF][Code]

​ 		​

2022

​
​ Noisy Labels are Treasure: Mean-Teacher-Assisted Confident Learning for Hepatic Vessel Segmentation,
​ Zhe Xu, Donghuan Lu, Yixin Wang, Jie Luo, Jayender Jagadeesan, Kai Ma, Yefeng Zheng, Xiu Li,
​ Medical Image Computing and Computer Assisted Intervention (MICCAI 2022) [PDF][Code] ​
​ Trust it or not: Confidence-guided automatic radiology report generation,
​ Yixin Wang, Zihao Lin, Zhe Xu, Haoyu Dong, Jiang Tian, Jie Luo, Zhongchao Shi, Yang Zhang, Jianping Fan, Zhiqiang He
​ Under review [PDF] ​
​ Cross-domain few-shot learning for rare-disease skin lesion segmentation,
​ Yixin Wang, Zhe Xu, Jiang Tian, Jie Luo, Zhongchao Shi, Yang Zhang, Jianping Fan, Zhiqiang He
​ IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022) [PDF] ​
​ Incorporating Uncertainty into Path Planning for Minimally Invasive Robotic Neurosurgery,
​ Sarah Frisken, Jie Luo, Nazim Haouchine, Steve Pieper, Yixin Wang, William M Wells, Alexandra J Golby
​ IEEE Transactions on Medical Robotics and Bionics [PDF] ​
​ All-around real label supervision: Cyclic prototype consistency learning for semi-supervised medical image segmentation,
​ Zhe Xu, Yixin Wang, Donghuan Lu, Lequan Yu, Jiangpeng Yan, Jie Luo, Kai Ma, Yefeng Zheng, Raymond Kai-yu Tong
​ IEEE Journal of Biomedical and Health Informatics (JBHI) [PDF] ​
​ On the dataset quality control for image registration evaluation,
​ Jie Luo, Guangshen Ma, Nazim Haouchine, Zhe Xu, Yixin Wang, Tina Kapur, Lipeng Ning, William M Wells III, Sarah Frisken
​ International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2022) [PDF] ​

2021
ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities,
Yixin Wang, Yang Zhang, Yang Liu, Zihao Lin, Jiang Tian, Cheng Zhong, Zhongchao Shi, Jianping Fan, Zhiqiang He,
Medical Image Computing and Computer Assisted Intervention (MICCAI 2021) [PDF][Code]
Modality-Pairing Learning for Brain Tumor Segmentation,
Yixin Wang, Yao Zhang, Feng Hou, Yang Liu, Jiang Tian, Cheng Zhong, Yang Zhang, Zhiqiang He,
BrainLes, Medical Image Computing and Computer Assisted Intervention (MICCAI 2021) [PDF][Code]
The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge,
Nicholas Heller, Fabian Isensee, Klaus H. Maier-Hein, Xiaoshuai Hou, Chunmei Xie, Fengyi Li, Yang Nan, Guangrui Mu, Zhiyong Lin, Miofei Han, Guang Yao, Yaozong Gao, Yao Zhang, Yixin Wang, Feng Hou, Jiawei Yang, Guangwei Xiong, Jiang Tian, Cheng Zhong, Jun Ma, Jack Rickman, Joshua Dean, Bethany Stai, Resha Tejpaul, Makinna Oestreich, Paul Blake, Heather Kaluzniak, Shaneabbas Raza, Joel Rosenberg, Keenan Moore, Edward Walczak, Zachary Rengel, Zach Edgerton, Ranveer Vasdev, Matthew Peterson, Sean McSweeney, Sarah Peterson, Arveen Kalapara, Niranjan Sathianathen, Nikolaos Papanikolopoulos, Christopher Weight,
Medical Image Analysis 2021, [PDF]
Does Non-COVID19 Lung Lesion Help? Investigating Transferability in COVID-19 CT Image Segmentation,
Yixin Wang, Yao Zhang, Yang Liu, Jiang Tian, Cheng Zhong, Zhongchao Shi, Yang Zhang, Zhiqiang He,
Computer Methods and Programs in Biomedicine, [PDF]

2020
Double-Uncertainty Weighted Method for Semi-supervised Learning,
Yixin Wang, Yao Zhang, Jiang Tian, Cheng Zhong, Zhongchao Shi, Yang Zhang, Zhiqiang He
Medical Image Computing and Computer Assisted Intervention (MICCAI 2020) [PDF]
Towards Data-Efficient Learning: A Benchmark for COVID-19 CT Lung and Infection Segmentation,
Jun Ma, Yixin Wang, Xingle An, Cheng Ge, Ziqi Yu, Jianan Chen, Qiongjie Zhu, Guoqiang Dong, Jian He, Zhiqiang He, Ziwei Nie, Xiaoping Yang
Medical Physics, [PDF]
FGB: Feature Guidance Branch for Organ Detection in Medical Images,
Yixin Wang, Yao Zhang, Li Liu, Cheng Zhong, Jiang Tian, Yang Zhang, Zhongchao Shi, Zhiqiang He
2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) [PDF]
How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study,
Jun Ma, Zhan Wei, Yiwen Zhang, Yixin Wang, Rongfei Lv, Cheng Zhu, Gaoxiang Chen, Jianan Liu, Chao Peng, Lei Wang, Yunpeng Wang, Jianan Chen
Medical Imaging with Deep Learning (MIDL 2020) [PDF][Code]
Semi-supervised Cardiac Image Segmentation via Label Propagation and Style Transfer,
Yao Zhang, Jiawei Yang, Feng Hou, Yang Liu, Yixin Wang, JiangTian, Cheng Zhong, Yang Zhang, and Zhiqiang He
Statistical Atlases and Computational Modelling of the Heart(STACOM 2020), Medical Image Computing and Computer Assisted Intervention (MICCAI 2020) [PDF]
Cascaded Volumetric Convolutional Network for Kidney Tumor Segmentation from CT volume,
Yao Zhang, Yixin Wang, Feng Hou, Jiawei Yang, Guangwei Xiong, Jiang Tian, Cheng Zhong
2019 Kidney Tumor Segmentation Challenge: KiTS19 [PDF]

Honors & Awards

  • School of Engineering Fellowship, Stanford University (2022)
  • CAS Presidential Scholarship (2022)
  • Outstanding Graduate (2022)
  • National Scholarship * 4 (2016; 2017; 2018; 2021)
  • MICCAI BraTS Challenge 2nd Place (2020)
  • MICCAI M&Ms Challenge 2nd Place (2020)
  • MICCAI KiTS Challenge 4th Place (2019)
  • Outstanding Student Cadre (2016;2017; 2018)
  • Top 10 College Students (2019)
  • Principal's Scholarship (2019)
  • College Innovation Scholarship (2017)
  • International “Mathematical Contest in Modeling” Honorable Mention (2017)
  • "Challenge Cup" National College Student Curricular Academic Science and Technology Works Competition National First prize (2018)

Professional Services

Conference Review

  • Conference on Information and Knowledge Management (CIKM), 2023
  • International Conference on Computer Vision (ICCV), 2021, 2023
  • International Conference on Machine Learning (ICML), 2021, 2022, 2023
  • The British Machine Vision Conference (BMVC), 2021
  • Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021, 2022, 2023
  • International Conference on Learning Representations (ICLR), 2023

Journal Review

  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • Transactions on Intelligent Systems and Technology (TIST)
  • IEEE Transactions on Automation Science and Engineering (TASE)
  • Engineering Applications of Artificial Intelligence (EAAI)
  • Frontiers in Radiology

    • Teaching

    • Teaching Assistant for PSYC221/BIODS227: Machine Learning for Neuroimaging (Fall 2023), Stanford

    Fun Facts

    Image 1

    I love singing, running and snowboarding!! I am recently learning golf!

    Image 2

    I love Hiking! Hope I can finish all the National trails!

    Image 3

    I have a cute bichon frise Dodo in China! Miss him so much

    ​
    ​
    ​ ​
    ​ while (!deck.isInOrder()) { print 'Iteration ' + i; deck.shuffle(); i++; }